Search papers, labs, and topics across Lattice.
4
0
6
7
Achieving better video distillation quality isn't just about precision; it's about ensuring broad mode coverage during training.
DLAM achieves superior temporal consistency and policy performance by modeling transitions as distributional latent actions, fundamentally changing how we approach action generation in VLA tasks.
Relying only on affinity can lead to failures in noisy environments, but ANFI's dual approach to neighbor interactions significantly boosts robustness in person re-ID tasks.
VisCo not only compresses visual tokens more effectively than previous methods but also enhances model performance through innovative use of memory tokens.
